qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 11, 2026 · Apple M4
orca-mini:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
83 vs 55
Hardware Fit
73 vs 98
Quality Score
87 vs 37
Hardware
qwen3:14b orca-mini:7b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b orca-mini:7b
Tokens/sec11.124.4
First chunk500 msN/A
TTFT500 ms219 ms
Load time7.3 s0.4 s
Memory usage9.4 GB5.8 GB
Memory %39%18%
HW Fit Score Breakdown
qwen3:14b
Speed
25/50
TTFT
20/20
Memory
28/30
orca-mini:7b
Speed
38/50
TTFT
30/20
Memory
30/30
Quality
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
orca-mini:7b
Reasoning
8/20
Coding
1/20
Instruction
8/20
Structured
10/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest